---
title: "BanHADEX — paper by Raquib et al. (2026)"
description: "To address this, the authors built BanHADEX, which they present as the first Bangla hate speech dataset with human-written… 52 references."
authors: ["Faisal Hossain Raquib", "Akm Moshiur Rahman Mazumder", "Md Fahim", "Md Tahmid Hasan Fuad", "Md Farhan Ishmam", "Faria Sultana", "M Ashraful Amin", "Amin Ahsan Ali", "Akmmahbubur Rahman"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.2022/"
doi: "10.18653/v1/2026.acl-long.2022"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/raquib-2026-banhadex-explainable-hate-speech-detection/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/raquib-2026-banhadex-explainable-hate-speech-detection/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/) / BanHADEX: Towards Explainable HAte Speech Detection in Bangla Using Human Annotated EXplanation

# BanHADEX: Towards Explainable HAte Speech Detection in Bangla Using Human Annotated EXplanation

**Authors:** Faisal Hossain Raquib, Akm Moshiur Rahman Mazumder, Md Fahim, Md Tahmid Hasan Fuad, Md Farhan Ishmam, Faria Sultana, M Ashraful Amin, Amin Ahsan Ali and Akmmahbubur Rahman · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.2022/) · [PDF](https://aclanthology.org/2026.acl-long.2022.pdf) · [DOI 10.18653/v1/2026.acl-long.2022](https://doi.org/10.18653/v1/2026.acl-long.2022) · [OpenAlex](https://openalex.org/W7166796783)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Bangla is spoken by more than 240 million people, yet existing Bangla hate speech resources only assign labels and never say why a comment counts as hateful. LLMs can produce explanations, but they often hallucinate or give long, hard-to-follow justifications. To address this, the authors built BanHADEX, which they present as the first Bangla hate speech dataset with human-written explanations. It contains 19,203 cleaned YouTube comments posted between April 2024 and June 2025. Each comment has a binary hate label, and hateful comments also have a fine-grained category, a target group, and a short rationale. Labels were assigned in a two-stage process and settled by majority vote. The authors then benchmarked open and closed LLMs under four prompting strategies and with LoRA fine-tuning. Fine-tuning with LoRA guided by the explanations gave the best results among open models for both classification and explanation quality. The resource lays groundwork for transparent content moderation in under-resourced, morphologically rich languages.

## Key points
- **Dataset composition:** BanHADEX has 10,048 non-hate and 9,155 hate comments, a hate-to-non-hate ratio of 0.91. The comments come from five video categories. Each hateful comment is tagged with one of seven hate categories and one of seven target groups.
- **Data cleaning:** Removing duplicates and non-essential entries eliminated 1,236 items. Links, hashtags, usernames and mentions were also stripped to protect user privacy.
- **Annotation:** Four native-speaker undergraduates labeled the data. Class labels were decided by majority vote, while each explanation was written by a single annotator and then checked through expert evaluation.
- **Model results:** The "Why H/NH" prompting strategy works well for closed models. Explanation-guided LoRA yields consistent gains in both classification and explanation.
- **Remaining difficulties:** Fine-grained category and target-group prediction are much harder than binary detection, with the Political target group the hardest. Including the video title in prompts helps zero-shot classification, but it lowers performance when the model must also generate an explanation.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Utah](https://md.research.elamur.ai/free/en/universities/university-of-utah/) — University, Salt Lake City, United States · 38 works · 5,925 citations
- [University of Manitoba](https://md.research.elamur.ai/free/en/universities/university-of-manitoba/) — University, Winnipeg, Canada · 5 works · 2,378 citations
- [Rajshahi University of Engineering and Technology](https://md.research.elamur.ai/free/en/universities/rajshahi-university-of-engineering-and-technology/) — University, Rajshahi, Bangladesh · 3 works

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works

🧭 Topics (2): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 972 works · [🛡️ Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · 517 works

## Cite

Cite as: Faisal Hossain Raquib, Akm Moshiur Rahman Mazumder, Md Fahim, Md Tahmid Hasan Fuad, Md Farhan Ishmam, Faria Sultana, M Ashraful Amin, Amin Ahsan Ali and Akmmahbubur Rahman. 2026. BanHADEX: Towards Explainable HAte Speech Detection in Bangla Using Human Annotated EXplanation. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{raquib2026banhadex,
  title = {{BanHADEX: Towards Explainable HAte Speech Detection in Bangla Using Human Annotated EXplanation}},
  author = {Faisal Hossain Raquib, Akm Moshiur Rahman Mazumder, Md Fahim, Md Tahmid Hasan Fuad, Md Farhan Ishmam, Faria Sultana, M Ashraful Amin, Amin Ahsan Ali and Akmmahbubur Rahman},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.2022},
  url = {https://doi.org/10.18653/v1/2026.acl-long.2022}
}
```

- [← previous BanglaSummEval: Reference-Free Factual Consistency Evaluation for Bangla Summarization](https://md.research.elamur.ai/free/en/papers/rafid-2026-banglasummeval-reference-free-factual-consistency/)
- [next → BanSuite: A Unified Toolkit and Software Platform for Low-Resource NLP in Bangla](https://md.research.elamur.ai/free/en/papers/sayed-2026-bansuite-unified-toolkit-software-platform/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/)

## References

52 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Fahim Ahmed, Md Fahim, Md Ashraful Amin, Amin Ahsan Ali, and AKM Rahman. 2024. Improving the performance of transformer-based models over classical baselines in multiple transliterated languages. In ECAI 2024, pages 4043–4050. IOS Press. [find](https://scholar.google.com/scholar?q=Fahim+Ahmed%2C+Md+Fahim%2C+Md+Ashraful+Amin%2C+Amin+Ahsan+Ali%2C+and+AKM+Rahman%2E+2024%2E+Improving+the+performance+of+transformer%2Dbased+models+over+classical+baselines+in+multiple+transliterated+languages%2E+In+E)
2. Md. Tofael Ahmed, Maqsudur Rahman, Shafayet Nur, Azm Islam, and Dipankar Das. 2021. Deployment of machine learning and deep learning algorithms in detecting cyberbullying in bangla and romanized bangla text: A comparative study. In 2021 International Conference on Advances in Electrical, Computing,… [find](https://scholar.google.com/scholar?q=Md%2E+Tofael+Ahmed%2C+Maqsudur+Rahman%2C+Shafayet+Nur%2C+Azm+Islam%2C+and+Dipankar+Das%2E+2021%2E+Deployment+of+machine+learning+and+deep+learning+algorithms+in+detecting+cyberbullying+in+bangla+and+romanized+bangl)
3. Sadia Alam, Md Farhan Ishmam, Navid Hasin Alvee, Md Shahnewaz Siddique, Md Azam Hossain, and Abu Raihan Mostofa Kamal. 2025. BnSentMix: A diverse Bengali-English code-mixed dataset for sentiment analysis. In Proceedings of the First Workshop on Language Models for Low-Resource Languages, pages 68–77… [find](https://scholar.google.com/scholar?q=Sadia+Alam%2C+Md+Farhan+Ishmam%2C+Navid+Hasin+Alvee%2C+Md+Shahnewaz+Siddique%2C+Md+Azam+Hossain%2C+and+Abu+Raihan+Mostofa+Kamal%2E+2025%2E+BnSentMix%3A+A+diverse+Bengali%2DEnglish+code%2Dmixed+dataset+for+sentiment+analy)
4. Sai Suman Aluru, Binny Mathew, Punyajoy Saha, and Animesh Mukherjee. 2020. Deep learning models for multilingual hate speech detection. arXiv preprint arXiv:2004.06465. — [arXiv:2004.06465](https://arxiv.org/abs/2004.06465) [find](https://scholar.google.com/scholar?q=Sai+Suman+Aluru%2C+Binny+Mathew%2C+Punyajoy+Saha%2C+and+Animesh+Mukherjee%2E+2020%2E+Deep+learning+models+for+multilingual+hate+speech+detection%2E+arXiv+preprint+arXiv%3A2004%2E06465%2E+%E2%80%94+%5BarXiv%3A2004%2E06465%5D%28https%3A%2F%2Far)
5. Dimosthenis Antypas and Jose Camacho-Collados. 2023. Robust hate speech detection in social media: A cross-dataset empirical evaluation. In The 7th Workshop on Online Abuse and Harms (WOAH), pages 231–242. [find](https://scholar.google.com/scholar?q=Dimosthenis+Antypas+and+Jose+Camacho%2DCollados%2E+2023%2E+Robust+hate+speech+detection+in+social+media%3A+A+cross%2Ddataset+empirical+evaluation%2E+In+The+7th+Workshop+on+Online+Abuse+and+Harms+%28WOAH%29%2C+pages+231)
6. Tasnim Tarannum Aurpa, Rifat Sadik, and Md Saiful Ahmed. 2022. Abusive bangla comments detection on facebook using transformer-based deep learning models. Social Network Analysis and Mining, 12(1):24. [find](https://scholar.google.com/scholar?q=Tasnim+Tarannum+Aurpa%2C+Rifat+Sadik%2C+and+Md+Saiful+Ahmed%2E+2022%2E+Abusive+bangla+comments+detection+on+facebook+using+transformer%2Dbased+deep+learning+models%2E+Social+Network+Analysis+and+Mining%2C+12%281%29%3A24%2E)
7. Nayan Banik and Md Hasan Hafizur Rahman. 2019. Toxicity detection on bengali social media comments using supervised models. In 2019 2nd international conference on Innovation in Engineering and Technology (ICIET), pages 1–5. IEEE. [find](https://scholar.google.com/scholar?q=Nayan+Banik+and+Md+Hasan+Hafizur+Rahman%2E+2019%2E+Toxicity+detection+on+bengali+social+media+comments+using+supervised+models%2E+In+2019+2nd+international+conference+on+Innovation+in+Engineering+and+Techno)
8. Tanveer Ahmed Belal, G. M. Shahariar, and Md. Hasanul Kabir. 2023. Interpretable multi labeled bengali toxic comments classification using deep learning. In 2023 International Conference on Electrical, Computer and Communication Engineering (ECCE), pages 1–6. [find](https://scholar.google.com/scholar?q=Tanveer+Ahmed+Belal%2C+G%2E+M%2E+Shahariar%2C+and+Md%2E+Hasanul+Kabir%2E+2023%2E+Interpretable+multi+labeled+bengali+toxic+comments+classification+using+deep+learning%2E+In+2023+International+Conference+on+Electrical)
9. Fariha Tahosin Boishakhi, Ponkoj Chandra Shill, and Md. Golam Rabiul Alam. 2021. Multi-modal hate speech detection using machine learning. In 2021 IEEE International Conference on Big Data (Big Data), pages 4496–4499. [find](https://scholar.google.com/scholar?q=Fariha+Tahosin+Boishakhi%2C+Ponkoj+Chandra+Shill%2C+and+Md%2E+Golam+Rabiul+Alam%2E+2021%2E+Multi%2Dmodal+hate+speech+detection+using+machine+learning%2E+In+2021+IEEE+International+Conference+on+Big+Data+%28Big+Data%29%2C)
10. Saugata Bose and Guoxin Su. 2022. Deep One-Class Hate Speech Detection Model. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 7040–7048, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Saugata+Bose+and+Guoxin+Su%2E+2022%2E+Deep+One%2DClass+Hate+Speech+Detection+Model%2E+In+Proceedings+of+the+Thirteenth+Language+Resources+and+Evaluation+Conference%2C+pages+7040%E2%80%937048%2C+Marseille%2C+France%2E+Europea)
11. Amit Kumar Das, Abdullah Al Asif, Anik Paul, and Md Nur Hossain. 2021. Bangla hate speech detection on social media using attention-based recurrent neural network. Journal of Intelligent Systems, 30(1):578–591. [find](https://scholar.google.com/scholar?q=Amit+Kumar+Das%2C+Abdullah+Al+Asif%2C+Anik+Paul%2C+and+Md+Nur+Hossain%2E+2021%2E+Bangla+hate+speech+detection+on+social+media+using+attention%2Dbased+recurrent+neural+network%2E+Journal+of+Intelligent+Systems%2C+30%281)
12. Md Farhad Alam Bhuiyan. 2025b. Banth: A multi-label hate speech detection dataset for transliterated bangla. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 7217–7236. [find](https://scholar.google.com/scholar?q=Md+Farhad+Alam+Bhuiyan%2E+2025b%2E+Banth%3A+A+multi%2Dlabel+hate+speech+detection+dataset+for+transliterated+bangla%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+NAACL+2025%2C+pages+7217%E2%80%937236%2E)
13. Thomas Davidson, Dana Warmsley, Michael Macy, and Ingmar Weber. 2017. [Automated hate speech detection and the problem of offensive language](https://md.research.elamur.ai/free/en/papers/davidson-2017-automated-hate-speech-detection-problem/). In Proceedings of the international AAAI conference on web and social media, volume 11, pages 512–515.
14. MD. Nahid Hasan, Kazi Shadman Sakib, Taghrid Tahani Preeti, Jeza Allohibi, Abdul-majeed Atiah Alharbi, and Jia Uddin. 2024. Olf-ml: An offensive language framework for detection, categorization, and offense target identification using text processing and machine learning algorithms. Mathematics, 12(… [find](https://scholar.google.com/scholar?q=MD%2E+Nahid+Hasan%2C+Kazi+Shadman+Sakib%2C+Taghrid+Tahani+Preeti%2C+Jeza+Allohibi%2C+Abdul%2Dmajeed+Atiah+Alharbi%2C+and+Jia+Uddin%2E+2024%2E+Olf%2Dml%3A+An+offensive+language+framework+for+detection%2C+categorization%2C+and+o)
15. Chiara Di Bonaventura, Lucia Siciliani, Pierpaolo Basile, Albert Merono Penuela, and Barbara Mcgillivray. 2024. Is explanation all you need? an expert survey on LLM-generated explanations for abusive language detection. In Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC… [find](https://scholar.google.com/scholar?q=Chiara+Di+Bonaventura%2C+Lucia+Siciliani%2C+Pierpaolo+Basile%2C+Albert+Merono+Penuela%2C+and+Barbara+Mcgillivray%2E+2024%2E+Is+explanation+all+you+need%3F+an+expert+survey+on+LLM%2Dgenerated+explanations+for+abusive+)
16. Estiak Ahmed Emon, Shihab Rahman, Joti Banarjee, Amit Kumar Das, and Tanni Mittra. 2019. A deep learning approach to detect abusive bengali text. In 2019 7th International Conference on Smart Computing and Communications (ICSCC), pages 1–5. [find](https://scholar.google.com/scholar?q=Estiak+Ahmed+Emon%2C+Shihab+Rahman%2C+Joti+Banarjee%2C+Amit+Kumar+Das%2C+and+Tanni+Mittra%2E+2019%2E+A+deep+learning+approach+to+detect+abusive+bengali+text%2E+In+2019+7th+International+Conference+on+Smart+Computin)
17. Md Fahim. 2023. Aambela at blp-2023 task 2: Enhancing banglabert performance for bangla sentiment analysis task with in task pretraining and adversarial weight perturbation. In Proceedings of the First Workshop on Bangla Language Processing (BLP-2023), pages 317–323. [find](https://scholar.google.com/scholar?q=Md+Fahim%2E+2023%2E+Aambela+at+blp%2D2023+task+2%3A+Enhancing+banglabert+performance+for+bangla+sentiment+analysis+task+with+in+task+pretraining+and+adversarial+weight+perturbation%2E+In+Proceedings+of+the+Firs)
18. Md Fahim, Fariha Tanjim Shifat, Fabiha Haider, Deeparghya Dutta Barua, MD Sakib Ul Rahman Sourove, Md Farhan Ishmam, and Md Farhad Alam Bhuiyan. 2024. Banglatlit: A benchmark dataset for back-transliteration of romanized bangla. In Findings of the Association for Computational Linguistics: EMNLP 202… [find](https://scholar.google.com/scholar?q=Md+Fahim%2C+Fariha+Tanjim+Shifat%2C+Fabiha+Haider%2C+Deeparghya+Dutta+Barua%2C+MD+Sakib+Ul+Rahman+Sourove%2C+Md+Farhan+Ishmam%2C+and+Md+Farhad+Alam+Bhuiyan%2E+2024%2E+Banglatlit%3A+A+benchmark+dataset+for+back%2Dtranslit)
19. Vaibhav Goel, Dhruv Sahnan, Saptarshi Dutta, Anil Bandhakavi, and Tanmoy Chakraborty. 2023. Hate-mongers ride on echo chambers to escalate hate speech diffusion. arXiv preprint arXiv:2302.02479. https://arxiv.org/abs/2302.02479. — [arXiv:2302.02479](https://arxiv.org/abs/2302.02479) [↗](https://arxiv.org/abs/2302.02479)
20. Maya Gudka, Kirsty LK Gardiner, and Tim Lomas. 2023. Towards a framework for flourishing through social media: A systematic review of 118 research studies. The Journal of Positive Psychology, 18(1):86–105. [find](https://scholar.google.com/scholar?q=Maya+Gudka%2C+Kirsty+LK+Gardiner%2C+and+Tim+Lomas%2E+2023%2E+Towards+a+framework+for+flourishing+through+social+media%3A+A+systematic+review+of+118+research+studies%2E+The+Journal+of+Positive+Psychology%2C+18%281%29%3A86)
21. Fabiha Haider, Md Farhan Ishmam, Fariha Tanjim Shifat, Md Tasmim Rahman Adib, Md Fahim, and Md Farhad Alam Bhuiyan. 2025a. Robustness of LLMs to transliteration perturbations in Bangla. In Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), pages 338–346, Mumbai, India. Asso… [find](https://scholar.google.com/scholar?q=Fabiha+Haider%2C+Md+Farhan+Ishmam%2C+Fariha+Tanjim+Shifat%2C+Md+Tasmim+Rahman+Adib%2C+Md+Fahim%2C+and+Md+Farhad+Alam+Bhuiyan%2E+2025a%2E+Robustness+of+LLMs+to+transliteration+perturbations+in+Bangla%2E+In+Proceedings)
22. Fabiha Haider, Fariha Tanjim Shifat, Md Farhan Ishmam, Md Sakib Ul Rahman Sourove, Deeparghya Dutta Barua, Md Fahim, and E. Hashmi and S. Y. Yayilgan. 2024. Multi-class Hate Speech Detection in the Norwegian Language Using FAST-RNN and Multilingual Fine-Tuned Transformers. Complex Intelligent System… [find](https://scholar.google.com/scholar?q=Fabiha+Haider%2C+Fariha+Tanjim+Shifat%2C+Md+Farhan+Ishmam%2C+Md+Sakib+Ul+Rahman+Sourove%2C+Deeparghya+Dutta+Barua%2C+Md+Fahim%2C+and+E%2E+Hashmi+and+S%2E+Y%2E+Yayilgan%2E+2024%2E+Multi%2Dclass+Hate+Speech+Detection+in+the+No)
23. Jawad Hossain, Avishek Das, Mohammed Moshiul Hoque, and Nazmul Siddique. 2023. Multilabel aggressive text classification from social media using transformer-based approaches. In 2023 26th International Conference on Computer and Information Technology (ICCIT), pages 1–6. [find](https://scholar.google.com/scholar?q=Jawad+Hossain%2C+Avishek+Das%2C+Mohammed+Moshiul+Hoque%2C+and+Nazmul+Siddique%2E+2023%2E+Multilabel+aggressive+text+classification+from+social+media+using+transformer%2Dbased+approaches%2E+In+2023+26th+Internationa)
24. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). ICLR, 1(2):3.
25. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2025. [A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/). ACM Transactions on Information Systems,…
26. Refa Annisatul Ilma, Setiawan Hadi, and Afrida Helen. 2021. Twitter’s hate speech multi-label classification using bidirectional long short-term memory (bilstm) method. In 2021 International Conference on Artificial Intelligence and Big Data Analytics, pages 93–99. [find](https://scholar.google.com/scholar?q=Refa+Annisatul+Ilma%2C+Setiawan+Hadi%2C+and+Afrida+Helen%2E+2021%2E+Twitter%E2%80%99s+hate+speech+multi%2Dlabel+classification+using+bidirectional+long+short%2Dterm+memory+%28bilstm%29+method%2E+In+2021+International+Conferenc)
27. Asim Irfan, Danish Azeem, Sanam Narejo, and Naresh Kumar. 2024. Multi-modal hate speech recognition through machine learning. In 2024 IEEE 1st Karachi Section Humanitarian Technology Conference (KHI-HTC), pages 1–6. [find](https://scholar.google.com/scholar?q=Asim+Irfan%2C+Danish+Azeem%2C+Sanam+Narejo%2C+and+Naresh+Kumar%2E+2024%2E+Multi%2Dmodal+hate+speech+recognition+through+machine+learning%2E+In+2024+IEEE+1st+Karachi+Section+Humanitarian+Technology+Conference+%28KHI%2DH)
28. Khondoker Ittehadul Islam, Sudipta Kar, Md Saiful Islam, and Mohammad Ruhul Amin. 2021. Sentnob: A dataset for analysing sentiment on noisy bangla texts. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3265–3271. [find](https://scholar.google.com/scholar?q=Khondoker+Ittehadul+Islam%2C+Sudipta+Kar%2C+Md+Saiful+Islam%2C+and+Mohammad+Ruhul+Amin%2E+2021%2E+Sentnob%3A+A+dataset+for+analysing+sentiment+on+noisy+bangla+texts%2E+In+Findings+of+the+Association+for+Computation)
29. Sarif Sultan Saruar Jahan, Raqeebir Rab, Peom Dutta, Hossain Muhammad Mahdi Hassan Khan, Muhammad Shahariar Karim Badhon, Sumaiya Binte Hassan, and Ashikur Rahman. 2023. Deep learning based misogynistic bangla text identification from social media. Computing and Informatics, 42(4):993–1012. [find](https://scholar.google.com/scholar?q=Sarif+Sultan+Saruar+Jahan%2C+Raqeebir+Rab%2C+Peom+Dutta%2C+Hossain+Muhammad+Mahdi+Hassan+Khan%2C+Muhammad+Shahariar+Karim+Badhon%2C+Sumaiya+Binte+Hassan%2C+and+Ashikur+Rahman%2E+2023%2E+Deep+learning+based+misogynist)
30. Andreas M. Kaplan and Michael Haenlein. 2010. Users of the world, unite! the challenges and opportunities of social media. Business Horizons, 53(1):59–68. [find](https://scholar.google.com/scholar?q=Andreas+M%2E+Kaplan+and+Michael+Haenlein%2E+2010%2E+Users+of+the+world%2C+unite%21+the+challenges+and+opportunities+of+social+media%2E+Business+Horizons%2C+53%281%29%3A59%E2%80%9368%2E)
31. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
32. Oscar Mañas, Benno Krojer, and Aishwarya Agrawal. 2024. Improving automatic vqa evaluation using large language models. In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symp… [find](https://scholar.google.com/scholar?q=Oscar+Ma%C3%B1as%2C+Benno+Krojer%2C+and+Aishwarya+Agrawal%2E+2024%2E+Improving+automatic+vqa+evaluation+using+large+language+models%2E+In+Proceedings+of+the+Thirty%2DEighth+AAAI+Conference+on+Artificial+Intelligence+a)
33. Binny Mathew, Punyajoy Saha, Seid Muhie Yimam, Chris Biemann, Pawan Goyal, and Animesh Mukherjee. 2021. Hatexplain: A benchmark dataset for explainable hate speech detection. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17):14867–14875. [find](https://scholar.google.com/scholar?q=Binny+Mathew%2C+Punyajoy+Saha%2C+Seid+Muhie+Yimam%2C+Chris+Biemann%2C+Pawan+Goyal%2C+and+Animesh+Mukherjee%2E+2021%2E+Hatexplain%3A+A+benchmark+dataset+for+explainable+hate+speech+detection%2E+Proceedings+of+the+AAAI+C)
34. Harshkumar Mehta and Kalpdrum Passi. 2022. Social media hate speech detection using explainable artificial intelligence (xai). Algorithms, 15(8). [find](https://scholar.google.com/scholar?q=Harshkumar+Mehta+and+Kalpdrum+Passi%2E+2022%2E+Social+media+hate+speech+detection+using+explainable+artificial+intelligence+%28xai%29%2E+Algorithms%2C+15%288%29%2E)
35. Md Ayon Mia, Akm Moshiur Rahman Mazumder, Khadiza Sultana Sayma, Md Fahim, Md Tahmid Hasan Fuad, Muhammad Ibrahim Khan, and Akmmahbubur Rahman. 2025. Banmime: Misogyny detection with metaphor explanation on bangla memes. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language… [find](https://scholar.google.com/scholar?q=Md+Ayon+Mia%2C+Akm+Moshiur+Rahman+Mazumder%2C+Khadiza+Sultana+Sayma%2C+Md+Fahim%2C+Md+Tahmid+Hasan+Fuad%2C+Muhammad+Ibrahim+Khan%2C+and+Akmmahbubur+Rahman%2E+2025%2E+Banmime%3A+Misogyny+detection+with+metaphor+explanat)
36. Nedjma Ousidhoum, Zizheng Lin, Hongming Zhang, Yangqiu Song, and Dit-Yan Yeung. 2019. [Multilingual and multi-aspect hate speech analysis](https://md.research.elamur.ai/free/en/papers/ousidhoum-2019-multilingual-multi-aspect-hate-speech/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processin…
37. Paloma Piot and Javier Parapar. 2025. Towards efficient and explainable hate speech detection via model distillation. In European Conference on Information Retrieval, pages 376–392. Springer. [find](https://scholar.google.com/scholar?q=Paloma+Piot+and+Javier+Parapar%2E+2025%2E+Towards+efficient+and+explainable+hate+speech+detection+via+model+distillation%2E+In+European+Conference+on+Information+Retrieval%2C+pages+376%E2%80%93392%2E+Springer%2E)
38. Faisal Hossain Raquib, Akm Moshiur Rahman Mazumder, Md Tahmid Hasan Fuad, Md Farhan Ishmam, and Md Fahim. 2025. BanHate: An upto-date and fine-grained Bangla hate speech dataset. In Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), pages 237–248, Mumbai, India. Association… [find](https://scholar.google.com/scholar?q=Faisal+Hossain+Raquib%2C+Akm+Moshiur+Rahman+Mazumder%2C+Md+Tahmid+Hasan+Fuad%2C+Md+Farhan+Ishmam%2C+and+Md+Fahim%2E+2025%2E+BanHate%3A+An+upto%2Ddate+and+fine%2Dgrained+Bangla+hate+speech+dataset%2E+In+Proceedings+of+the)
39. R Reghunathan and AS Asha. 2022. Hate speech detection in conventional language on social media by using machine learning. In International Journal of Engineering Research & Technology (IJERT), volume 11. [find](https://scholar.google.com/scholar?q=R+Reghunathan+and+AS+Asha%2E+2022%2E+Hate+speech+detection+in+conventional+language+on+social+media+by+using+machine+learning%2E+In+International+Journal+of+Engineering+Research+%26+Technology+%28IJERT%29%2C+volume)
40. Nasif Istiak Remon, Nafisa Hasan Tuli, and Ranit Debnath Akash. 2022. Bengali hate speech detection in public facebook pages. In 2022 International Conference on Innovations in Science, Engineering and Technology (ICISET), pages 169–173. [find](https://scholar.google.com/scholar?q=Nasif+Istiak+Remon%2C+Nafisa+Hasan+Tuli%2C+and+Ranit+Debnath+Akash%2E+2022%2E+Bengali+hate+speech+detection+in+public+facebook+pages%2E+In+2022+International+Conference+on+Innovations+in+Science%2C+Engineering+an)
41. Nauros Romim, Mosahed Ahmed, Hriteshwar Talukder, and Md Saiful Islam. 2021. Hate speech detection in the bengali language: A dataset and its baseline evaluation. In Proceedings of International Joint Conference on Advances in Computational Intelligence: IJCACI 2020, pages 457–468. Springer. [find](https://scholar.google.com/scholar?q=Nauros+Romim%2C+Mosahed+Ahmed%2C+Hriteshwar+Talukder%2C+and+Md+Saiful+Islam%2E+2021%2E+Hate+speech+detection+in+the+bengali+language%3A+A+dataset+and+its+baseline+evaluation%2E+In+Proceedings+of+International+Joint)
42. Md. Saifuddin, Mohiuddin Ahmed, Spandan Basu, and Pritam Acharjee. 2023. Enhancing online safety: Natural language processing based multi-label cyberbullying classification in bangla. In 2023 26th International Conference on Computer and Information Technology (ICCIT), pages 1–6. [find](https://scholar.google.com/scholar?q=Md%2E+Saifuddin%2C+Mohiuddin+Ahmed%2C+Spandan+Basu%2C+and+Pritam+Acharjee%2E+2023%2E+Enhancing+online+safety%3A+Natural+language+processing+based+multi%2Dlabel+cyberbullying+classification+in+bangla%2E+In+2023+26th+Int)
43. Keita Saito, Akifumi Wachi, Koki Wataoka, and Youhei Akimoto. 2023. Verbosity bias in preference labeling by large language models. ArXiv, abs/2310.10076. — [arXiv:2310.10076](https://arxiv.org/abs/2310.10076) [find](https://scholar.google.com/scholar?q=Keita+Saito%2C+Akifumi+Wachi%2C+Koki+Wataoka%2C+and+Youhei+Akimoto%2E+2023%2E+Verbosity+bias+in+preference+labeling+by+large+language+models%2E+ArXiv%2C+abs%2F2310%2E10076%2E+%E2%80%94+%5BarXiv%3A2310%2E10076%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F23)
44. Mahmudul Hasan Shakil. 2022. A hybrid deep learning model and explainable AI-based Bengali hate speech multi-label classification and interpretation. Ph.D. thesis, Brac University. [find](https://scholar.google.com/scholar?q=Mahmudul+Hasan+Shakil%2E+2022%2E+A+hybrid+deep+learning+model+and+explainable+AI%2Dbased+Bengali+hate+speech+multi%2Dlabel+classification+and+interpretation%2E+Ph%2ED%2E+thesis%2C+Brac+University%2E)
45. Omar Sharif, Eftekhar Hossain, and Mohammed Moshiul Hoque. 2022. M-bad: A multilabel dataset for detecting aggressive texts and their targets. In Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations, pages 75–85. [find](https://scholar.google.com/scholar?q=Omar+Sharif%2C+Eftekhar+Hossain%2C+and+Mohammed+Moshiul+Hoque%2E+2022%2E+M%2Dbad%3A+A+multilabel+dataset+for+detecting+aggressive+texts+and+their+targets%2E+In+Proceedings+of+the+Workshop+on+Combating+Online+Hostil)
46. Sinéad Walsh and Paul Greaney. 2025. Multiclass hate speech detection with an aggregated dataset. Natural Language Processing, page 1–17. [find](https://scholar.google.com/scholar?q=Sin%C3%A9ad+Walsh+and+Paul+Greaney%2E+2025%2E+Multiclass+hate+speech+detection+with+an+aggregated+dataset%2E+Natural+Language+Processing%2C+page+1%E2%80%9317%2E)
47. Jessica E. Wendorf and Fan Yang. 2015. Benefits of a negative post: Effects of computer-mediated venting on relationship maintenance. Computers in Human Behavior, 52:271–277. [find](https://scholar.google.com/scholar?q=Jessica+E%2E+Wendorf+and+Fan+Yang%2E+2015%2E+Benefits+of+a+negative+post%3A+Effects+of+computer%2Dmediated+venting+on+relationship+maintenance%2E+Computers+in+Human+Behavior%2C+52%3A271%E2%80%93277%2E)
48. Wikipedia. 2025. Bengali language speaker statistics. [https://en.wikipedia.org/wiki/Bengali_](https://en.wikipedia.org/wiki/Bengali_) language. Accessed: July 27, 2025. [↗](https://en.wikipedia.org/wiki/Bengali_)
49. Ziwei Xu, Sanjay Jain, and Mohan Kankanhalli. 2025. [Hallucination is inevitable: An innate limitation of large language models](https://md.research.elamur.ai/free/en/papers/xu-2024-hallucination-inevitable-innate-limitation-large/). Preprint, arXiv:2401.11817.
50. Yongjin Yang, Joonkee Kim, Yujin Kim, Namgyu Ho, James Thorne, and Se-Young Yun. 2023. Hare: Explainable hate speech detection with step-by-step reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5490–5505. [find](https://scholar.google.com/scholar?q=Yongjin+Yang%2C+Joonkee+Kim%2C+Yujin+Kim%2C+Namgyu+Ho%2C+James+Thorne%2C+and+Se%2DYoung+Yun%2E+2023%2E+Hare%3A+Explainable+hate+speech+detection+with+step%2Dby%2Dstep+reasoning%2E+In+Findings+of+the+Association+for+Computati)
51. Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Tianyi+Zhang%2A%2C+Varsha+Kishore%2A%2C+Felix+Wu%2A%2C+Kilian+Q%2E+Weinberger%2C+and+Yoav+Artzi%2E+2020%2E+Bertscore%3A+Evaluating+text+generation+with+bert%2E+In+International+Conference+on+Learning+Representations%2E)
52. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024. [Llamafactory: Unified efficient fine-tuning of 100+ language models](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/). In Proceedings of the 62nd ACL, Bangkok, Thailand. Association for Computational Linguistics.

*Updated 1 November 2026*